ESNs with one dimensional topography

Authors:
N. Michael Mayer;Matthew Browne;Horng Jason Wu
Affiliations:
Nat’l Chung Cheng University, Chia-Yi, Taiwan;Nat’l Chung Cheng University, Chia-Yi, Taiwan;Nat’l Chung Cheng University, Chia-Yi, Taiwan
Venue:
ICONIP'10 Proceedings of the 17th international conference on Neural information processing: models and applications - Volume Part II
Year:
2010

Citing 4
Cited 0

Self-Organizing Maps

Self-Organizing Maps
Poster abstract: Distributed fault detection using a recurrent neural network

IPSN '09 Proceedings of the 2009 International Conference on Information Processing in Sensor Networks
Time series causality inference using echo state networks

LVA/ICA'10 Proceedings of the 9th international conference on Latent variable analysis and signal separation
Collective Behavior of a Small-World Recurrent Neural System With Scale-Free Distribution

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper the standard Echo State approach is combined with a topography, i.e. it is assigned with a position which implies certain constraints of the mutual connectivity between these neurons. The overall design of the network allows certain neurons to process new information earlier than others. As a consequence the connectivity of the trained output layer can be analyzed; conclusions can be drawn regarding which reservoir depth is sufficient to process the given task. In particular we look at connection strengths of different locations of the reservoir as a function of the test error which can be influenced by using ridge regression.